Document Type

Article

Abstract

The abundance of on-line electronic financial news articles has opened up new possibilities for intelligent systems that could extract and organize relevant knowledge automatically in a usable format. While most typical information extraction systems require a hand-built dictionary of templates and, subsequently, are subject to ceaseless modification to accommodate new patterns that are observed in the text, in this research, we propose a novel text-based decision support system (DSS) that will (i) extract event sequences from shallow text patterns and (ii) predict the likelihood of the occurrence of events using a classifier-based inference engine. We investigated more than 2,000 financial reports with 28,000 sentences. Experiments show the DSS outperforms other similar statistical models.

Share

COinS